CAREERLLAMA: AN AI-POWERED PERSONALIZED CAREER RECOMMENDATION SYSTEM WITH PSYCHOMETRIC AND SKILL GAP INTEGRATION

Abstract

Career decision-making has become an increasingly complex cognitive and informational challenge, driven by the rapid evolution of industry demands and job roles. In the absence of adaptive and personalized guidance systems, individuals are often left to make suboptimal career choices, leading to skill mismatches, occupational dissatisfaction, and underutilization of workforce potential. These inefficiencies not only hinder personal development but also negatively affect organizational productivity and economic resilience. This study presents an intelligent, context-sensitive career recommendation framework powered by the LLaMA large language model, designed to generate personal- ized career pathways. The system synthesizes multi-dimensional user inputs—such as educational background, acquired skills, cognitive preferences, and psychometric traits—to provide data- driven career recommendations. Furthermore, the framework identifies existing skill gaps and suggests targeted upskilling strategies. By incorporating machine learning and natural lan- guage understanding into career planning, the proposed model offers a scalable solution to the growing misalignment between workforce capabilities and evolving occupational demands.